Video generation is slowly getting to the point where, not only can it produce solid results, but it can be accessed by those who are not-so technically inclined. Now, Adobe’s Firefly generative video component is finally going live in Premiere Pro.
Adobe Firefly’s generative video technology debuted in September and offers both text-to-video and image-to-video capabilities. You can now experiment with these features through the Premiere Pro beta app or a web beta. While Premiere Pro is limited to a Generative Extend feature, which uses AI to increase the length of an existing video, the web beta allows you to generate up to five seconds of video from text or image prompts, with customization options for camera movement and style.
Early impressions suggest that Firefly’s text-to-video model may not yet be as polished as those from competitors like Runway and OpenAI. We tried to give it a spin ourselves, but it’s currently behind a waitlist, and we have no clue whether we will be allowed in anytime soon. If you want to give this a spin, you’ll have to sign up for the waitlist as well.
If you try Firefly through the Premiere Pro app beta, available to all Premiere Pro customers, you’ll have the option to try Generative Extend. This feature seamlessly lengthens video clips by up to two seconds, even extending background audio without replicating copyrighted music or voices. Text-to-video generation is not available in Premiere Pro at the time of writing.
The company says it remains committed to responsible AI development, training Firefly on a curated dataset of commercially safe content and incorporating “AI-generated” watermarks in video metadata. Adobe also aims to address concerns among creatives by highlighting how AI tools can increase productivity and content demand, as many creatives feel that AI is a threat to their work, rather than an additional tool in their toolbox.
Source: Adobe via TechCrunch
